Pyright

Author: AlonsoGuevara

graphrag/config/models/graph_rag_config.py

@@ -40,8 +40,8 @@ def __str__(self):
         """Get a string representation."""
         return self.model_dump_json(indent=4)
 
-    root_dir: str | None = Field(
-        description="The root directory for the configuration.", default=None
+    root_dir: str = Field(
+        description="The root directory for the configuration.", default="."
     )
 
     reporting: ReportingConfig = Field(

graphrag/index/config/cache.py

@@ -7,8 +7,7 @@
 
 from typing import Generic, Literal, TypeVar
 
-from pydantic import BaseModel
-from pydantic import Field as pydantic_Field
+from pydantic import BaseModel, Field
 
 from graphrag.config.enums import CacheType
 
@@ -27,7 +26,7 @@ class PipelineFileCacheConfig(PipelineCacheConfig[Literal[CacheType.file]]):
     type: Literal[CacheType.file] = CacheType.file
     """The type of cache."""
 
-    base_dir: str | None = pydantic_Field(
+    base_dir: str | None = Field(
         description="The base directory for the cache.", default=None
     )
     """The base directory for the cache."""
@@ -53,22 +52,20 @@ class PipelineBlobCacheConfig(PipelineCacheConfig[Literal[CacheType.blob]]):
     type: Literal[CacheType.blob] = CacheType.blob
     """The type of cache."""
 
-    base_dir: str | None = pydantic_Field(
+    base_dir: str | None = Field(
         description="The base directory for the cache.", default=None
     )
     """The base directory for the cache."""
 
-    connection_string: str | None = pydantic_Field(
+    connection_string: str | None = Field(
         description="The blob cache connection string for the cache.", default=None
     )
     """The blob cache connection string for the cache."""
 
-    container_name: str | None = pydantic_Field(
-        description="The container name for cache", default=None
-    )
+    container_name: str = Field(description="The container name for cache", default="")
     """The container name for cache"""
 
-    storage_account_blob_url: str | None = pydantic_Field(
+    storage_account_blob_url: str | None = Field(
         description="The storage account blob url for cache", default=None
     )
     """The storage account blob url for cache"""

graphrag/index/config/input.py

@@ -7,8 +7,7 @@
 
 from typing import Generic, Literal, TypeVar
 
-from pydantic import BaseModel
-from pydantic import Field as pydantic_Field
+from pydantic import BaseModel, Field
 
 from graphrag.config.enums import InputFileType, InputType
 from graphrag.index.config.workflow import PipelineWorkflowStep
@@ -22,49 +21,47 @@ class PipelineInputConfig(BaseModel, Generic[T]):
     file_type: T
     """The file type of input."""
 
-    type: InputType | None = pydantic_Field(
+    type: InputType | None = Field(
         description="The input type to use.",
         default=None,
     )
     """The input type to use."""
 
-    connection_string: str | None = pydantic_Field(
+    connection_string: str | None = Field(
         description="The blob cache connection string for the input files.",
         default=None,
     )
     """The blob cache connection string for the input files."""
 
-    storage_account_blob_url: str | None = pydantic_Field(
+    storage_account_blob_url: str | None = Field(
         description="The storage account blob url for the input files.", default=None
     )
     """The storage account blob url for the input files."""
 
-    container_name: str | None = pydantic_Field(
+    container_name: str | None = Field(
         description="The container name for input files.", default=None
     )
     """The container name for the input files."""
 
-    base_dir: str | None = pydantic_Field(
+    base_dir: str | None = Field(
         description="The base directory for the input files.", default=None
     )
     """The base directory for the input files."""
 
-    file_pattern: str = pydantic_Field(
-        description="The regex file pattern for the input files."
-    )
+    file_pattern: str = Field(description="The regex file pattern for the input files.")
     """The regex file pattern for the input files."""
 
-    file_filter: dict[str, str] | None = pydantic_Field(
+    file_filter: dict[str, str] | None = Field(
         description="The optional file filter for the input files.", default=None
     )
     """The optional file filter for the input files."""
 
-    post_process: list[PipelineWorkflowStep] | None = pydantic_Field(
+    post_process: list[PipelineWorkflowStep] | None = Field(
         description="The post processing steps for the input.", default=None
     )
     """The post processing steps for the input."""
 
-    encoding: str | None = pydantic_Field(
+    encoding: str | None = Field(
         description="The encoding for the input files.", default=None
     )
     """The encoding for the input files."""
@@ -75,28 +72,28 @@ class PipelineCSVInputConfig(PipelineInputConfig[Literal[InputFileType.csv]]):
 
     file_type: Literal[InputFileType.csv] = InputFileType.csv
 
-    source_column: str | None = pydantic_Field(
+    source_column: str | None = Field(
         description="The column to use as the source of the document.", default=None
     )
     """The column to use as the source of the document."""
 
-    timestamp_column: str | None = pydantic_Field(
+    timestamp_column: str | None = Field(
         description="The column to use as the timestamp of the document.", default=None
     )
     """The column to use as the timestamp of the document."""
 
-    timestamp_format: str | None = pydantic_Field(
+    timestamp_format: str | None = Field(
         description="The format of the timestamp column, so it can be parsed correctly.",
         default=None,
     )
     """The format of the timestamp column, so it can be parsed correctly."""
 
-    text_column: str | None = pydantic_Field(
+    text_column: str | None = Field(
         description="The column to use as the text of the document.", default=None
     )
     """The column to use as the text of the document."""
 
-    title_column: str | None = pydantic_Field(
+    title_column: str | None = Field(
         description="The column to use as the title of the document.", default=None
     )
     """The column to use as the title of the document."""
@@ -108,7 +105,7 @@ class PipelineTextInputConfig(PipelineInputConfig[Literal[InputFileType.text]]):
     file_type: Literal[InputFileType.text] = InputFileType.text
 
     # Text Specific
-    title_text_length: int | None = pydantic_Field(
+    title_text_length: int | None = Field(
         description="Number of characters to use from the text as the title.",
         default=None,
     )

graphrag/index/config/pipeline.py

@@ -6,8 +6,7 @@
 from __future__ import annotations
 
 from devtools import pformat
-from pydantic import BaseModel
-from pydantic import Field as pydantic_Field
+from pydantic import BaseModel, Field
 
 from graphrag.index.config.cache import PipelineCacheConfigTypes
 from graphrag.index.config.input import PipelineInputConfigTypes
@@ -27,43 +26,41 @@ def __str__(self):
         """Get a string representation."""
         return str(self.model_dump_json(indent=4))
 
-    extends: list[str] | str | None = pydantic_Field(
+    extends: list[str] | str | None = Field(
         description="Extends another pipeline configuration", default=None
     )
     """Extends another pipeline configuration"""
 
-    input: PipelineInputConfigTypes | None = pydantic_Field(
+    input: PipelineInputConfigTypes | None = Field(
         default=None, discriminator="file_type"
     )
     """The input configuration for the pipeline."""
 
-    reporting: PipelineReportingConfigTypes | None = pydantic_Field(
+    reporting: PipelineReportingConfigTypes | None = Field(
         default=None, discriminator="type"
     )
     """The reporting configuration for the pipeline."""
 
-    storage: PipelineStorageConfigTypes | None = pydantic_Field(
+    storage: PipelineStorageConfigTypes | None = Field(
         default=None, discriminator="type"
     )
     """The storage configuration for the pipeline."""
 
-    update_index_storage: PipelineStorageConfigTypes | None = pydantic_Field(
+    update_index_storage: PipelineStorageConfigTypes | None = Field(
         default=None, discriminator="type"
     )
     """The storage configuration for the updated index."""
 
-    cache: PipelineCacheConfigTypes | None = pydantic_Field(
-        default=None, discriminator="type"
-    )
+    cache: PipelineCacheConfigTypes | None = Field(default=None, discriminator="type")
     """The cache configuration for the pipeline."""
 
-    root_dir: str | None = pydantic_Field(
+    root_dir: str | None = Field(
         description="The root directory for the pipeline. All other paths will be based on this root_dir.",
         default=None,
     )
     """The root directory for the pipeline."""
 
-    workflows: list[PipelineWorkflowReference] = pydantic_Field(
+    workflows: list[PipelineWorkflowReference] = Field(
         description="The workflows for the pipeline.", default_factory=list
     )
     """The workflows for the pipeline."""

graphrag/index/config/reporting.py

@@ -7,8 +7,7 @@
 
 from typing import Generic, Literal, TypeVar
 
-from pydantic import BaseModel
-from pydantic import Field as pydantic_Field
+from pydantic import BaseModel, Field
 
 from graphrag.config.enums import ReportingType
 
@@ -27,7 +26,7 @@ class PipelineFileReportingConfig(PipelineReportingConfig[Literal[ReportingType.
     type: Literal[ReportingType.file] = ReportingType.file
     """The type of reporting."""
 
-    base_dir: str | None = pydantic_Field(
+    base_dir: str | None = Field(
         description="The base directory for the reporting.", default=None
     )
     """The base directory for the reporting."""
@@ -48,23 +47,23 @@ class PipelineBlobReportingConfig(PipelineReportingConfig[Literal[ReportingType.
     type: Literal[ReportingType.blob] = ReportingType.blob
     """The type of reporting."""
 
-    connection_string: str | None = pydantic_Field(
+    connection_string: str | None = Field(
         description="The blob reporting connection string for the reporting.",
         default=None,
     )
     """The blob reporting connection string for the reporting."""
 
-    container_name: str | None = pydantic_Field(
-        description="The container name for reporting", default=None
+    container_name: str = Field(
+        description="The container name for reporting", default=""
     )
     """The container name for reporting"""
 
-    storage_account_blob_url: str | None = pydantic_Field(
+    storage_account_blob_url: str | None = Field(
         description="The storage account blob url for reporting", default=None
     )
     """The storage account blob url for reporting"""
 
-    base_dir: str | None = pydantic_Field(
+    base_dir: str | None = Field(
         description="The base directory for the reporting.", default=None
     )
     """The base directory for the reporting."""

graphrag/index/config/storage.py

@@ -7,8 +7,7 @@
 
 from typing import Generic, Literal, TypeVar
 
-from pydantic import BaseModel
-from pydantic import Field as pydantic_Field
+from pydantic import BaseModel, Field
 
 from graphrag.config.enums import StorageType
 
@@ -27,7 +26,7 @@ class PipelineFileStorageConfig(PipelineStorageConfig[Literal[StorageType.file]]
     type: Literal[StorageType.file] = StorageType.file
     """The type of storage."""
 
-    base_dir: str | None = pydantic_Field(
+    base_dir: str | None = Field(
         description="The base directory for the storage.", default=None
     )
     """The base directory for the storage."""
@@ -46,22 +45,22 @@ class PipelineBlobStorageConfig(PipelineStorageConfig[Literal[StorageType.blob]]
     type: Literal[StorageType.blob] = StorageType.blob
     """The type of storage."""
 
-    connection_string: str | None = pydantic_Field(
+    connection_string: str | None = Field(
         description="The blob storage connection string for the storage.", default=None
     )
     """The blob storage connection string for the storage."""
 
-    container_name: str | None = pydantic_Field(
-        description="The container name for storage", default=None
+    container_name: str = Field(
+        description="The container name for storage", default=""
     )
     """The container name for storage."""
 
-    base_dir: str | None = pydantic_Field(
+    base_dir: str | None = Field(
         description="The base directory for the storage.", default=None
     )
     """The base directory for the storage."""
 
-    storage_account_blob_url: str | None = pydantic_Field(
+    storage_account_blob_url: str | None = Field(
         description="The storage account blob url.", default=None
     )
     """The storage account blob url."""

graphrag/index/config/workflow.py

@@ -7,8 +7,7 @@
 
 from typing import Any
 
-from pydantic import BaseModel
-from pydantic import Field as pydantic_Field
+from pydantic import BaseModel, Field
 
 PipelineWorkflowStep = dict[str, Any]
 """Represent a step in a workflow."""
@@ -20,15 +19,15 @@
 class PipelineWorkflowReference(BaseModel):
     """Represent a reference to a workflow, and can optionally be the workflow itself."""
 
-    name: str | None = pydantic_Field(description="Name of the workflow.", default=None)
+    name: str | None = Field(description="Name of the workflow.", default=None)
     """Name of the workflow."""
 
-    steps: list[PipelineWorkflowStep] | None = pydantic_Field(
+    steps: list[PipelineWorkflowStep] | None = Field(
         description="The optional steps for the workflow.", default=None
     )
     """The optional steps for the workflow."""
 
-    config: PipelineWorkflowConfig | None = pydantic_Field(
+    config: PipelineWorkflowConfig | None = Field(
         description="The optional configuration for the workflow.", default=None
     )
     """The optional configuration for the workflow."""

graphrag/index/llm/mock_llm.py

@@ -45,4 +45,5 @@ async def __call__(
         )
 
     def child(self, name):
+        """Return a new mock LLM."""
         raise NotImplementedError